Sludge backflow control method, equipment and system based on AI decision control

Abstract

The invention provides a sludge backflow control method based on AI decision control and further provides corresponding equipment and system.The sludge backflow control method based on AI decision control comprises the steps that an execution mode command input by a user is obtained, and a corresponding execution mode is judged according to the execution mode command; starting a corresponding program according to the corresponding execution mode, and controlling the opening and closing of a sludge discharge pump / drainage flow pump based on an AI decision according to the sludge discharge / drainage data obtained in real time; according to the sludge backflow control method based on AI decision control, the sludge discharge / water discharge amount can be accurately controlled based on the AI decision, and real-time efficient treatment and accurate control of sludge discharge / water discharge data are realized.

Description

Technical Field

[0001] The present application relates to the field of sewage treatment, and specifically to a sludge return control method based on AI decision control, as well as corresponding equipment and systems. Background Art

[0002] In the field of sewage treatment, sludge return control based on AI decision-making control is a key link to ensure treatment effect and stable operation of the system. Traditional sludge return control technology based on AI decision-making control mainly relies on manual experience, simple mechanical devices or basic automation systems to achieve.

[0003] In terms of sludge discharge operation, it is common to manually turn on and off the sludge pump at a fixed time and roughly estimate the amount of sludge discharged. Mainly, the operator starts the sludge pump at a certain interval (such as one day or several hours) based on experience, and shuts it down after running for a period of time. Or as disclosed in an online sludge return control method and system with application number CN202210793737.8, the sludge return amount is adjusted by judging the numerical value of the first sludge concentration data and the second sludge concentration data. This method lacks precise control of the amount of sludge discharged, which can easily lead to excessive or insufficient sludge discharge. Excessive sludge discharge will cause serious loss of microorganisms in the treatment system, destroy the ecological balance of microorganisms, and greatly weaken the ability to treat sewage; too little sludge discharge will cause excessive accumulation of sludge in the system, occupy a large amount of space, hinder the normal operation of the treatment equipment, increase the risk of equipment blockage, and may also cause secondary pollution, making it difficult for the treated water quality to meet the standards. In terms of flow control, traditional methods usually use fixed flow settings or simple proportional adjustment methods. The existing slightly automated systems adjust the return or drainage flow rate according to a certain proportion based on the inlet flow rate; this adjustment method is relatively rough. When the inlet flow rate fluctuates greatly, the flow rate cannot be adjusted in time and effectively, resulting in unstable system treatment effect. For example, in the rainy season or peak water use period, when the inlet flow rate increases significantly, the treatment tank may overflow due to poor return or drainage, causing the sewage to be discharged without sufficient treatment; when the inlet flow rate is small, the concentration of effective microorganisms and substrates in the treatment tank may decrease due to excessive drainage, affecting the treatment efficiency. In terms of data processing, the traditional system makes insufficient use of the data collected by sensors and processes them simply. The data collected by the sensors may contain various errors and outliers, but the traditional technology lacks an effective data processing mechanism, which causes abnormal data to be mixed into the control process, interferes with the control accuracy, and makes it difficult for the system to accurately control the sludge return and sewage discharge process according to the actual situation.

[0004] In summary, the traditional sludge return control technology based on AI decision-making control has obvious deficiencies in terms of precise control of sludge discharge, dynamic flow adjustment and effective data processing. It is difficult to meet the increasing efficiency and quality requirements of modern sewage / sludge treatment, and it is urgently needed to be improved in all aspects. Summary of the invention

[0005] The purpose of this application is to solve the problem of intelligent control of sludge return.

[0006] To solve the above technical problems, this application provides a sludge return control method based on AI decision-making control, including: Obtain the execution mode command input by the user, and judge the corresponding execution mode according to the execution mode command; If it is judged to be the sludge discharge mode, obtain the preset expected sludge discharge amount data and pump frequency data; Turn on the sludge discharge pump and set the pump frequency of the sludge discharge pump according to the pump frequency data; Obtain the current sludge discharge amount data in real time; When the current sludge discharge amount data is not less than the expected sludge discharge amount data, turn off the sludge discharge pump.

[0007] Furthermore, the sludge return control method based on AI decision-making control further includes: If it is judged to be the manual setting flow target mode, obtain the manually set target drainage flow target value; turn on the drainage flow pump and obtain the real-time drainage amount data at a preset frequency; Judge whether the real-time drainage amount data is within the range of the manually set target drainage flow target value ±X; If the real-time drainage amount data is not within the range of the manually set target drainage flow target value ±X, use the PID (Proportional-Integral-Derivative) control algorithm to calculate the adjustment amount of the pump frequency, and then adjust the pump frequency according to the adjustment amount of the pump frequency; Return to the step of judging whether the real-time drainage amount data is within the range of the manually set target drainage flow target value ±X, until the real-time drainage amount data is within the range of the manually set target drainage flow target value ±X, then turn off the drainage flow pump.

[0008] Furthermore, the sludge return control method based on AI decision-making control further includes: If it is judged to be the automatic setting flow target mode, obtain the flow data of the water inlet at a preset frequency in real time; Turn on the drainage flow pump and obtain the real-time drainage amount data at a preset frequency; Calculate the automatic target drainage flow target value according to the flow data of the water inlet and the real-time drainage amount data; Turn on or off the drainage flow pump according to the automatic target drainage flow target value.

[0009] Furthermore, the step of turning on or off the drainage flow pump according to the automatic target drainage flow target value includes: Judge whether the real-time drainage amount data is within the range of the automatic target drainage flow target value ±X; If the real-time drainage volume data is not within the range of the automatic target drainage flow target value ±X, use the PID control algorithm to calculate the adjustment amount of the pump frequency, and adjust the pump frequency according to the adjustment amount of the pump frequency; Return to the step of judging whether the real-time drainage volume data is within the range of the automatic target drainage flow target value ±X, and close the drainage flow pump until the real-time drainage volume data is within the range of the automatic target drainage flow target value ±X.

[0010] Further, calculating the adjustment amount of the pump frequency using the PID control algorithm specifically includes: Use the following formula to calculate the adjustment amount of the pump frequency in real time: ; Wherein, is the last value of the flow gap time series , is the second last value of the flow gap time series , is the change trend of the flow gap time series, is the shortest adjustment time interval of the valve, and K represents the adjustment strength.

[0011] Further, before the step of obtaining the execution mode command input by the user, it further includes: Receive the time series data input by the sensor; Clean the time series data; Fill the vacant positions in the cleaned time series data with numbers; Sort the filled time series data according to time to form a new time series data.

[0012] Further, the step of cleaning the time series data includes: Identify the invalid input values in the time series data; Eliminate the invalid input values.

[0013] Further, the step of filling the vacant positions in the cleaned time series data with numbers includes: filling the vacant positions in the cleaned time series data with numbers according to the mean filling method; or filling the vacant positions in the cleaned time series data with numbers according to the median filling method.

[0014] To solve the above technical problems, the present application also provides a sludge return control device based on AI decision control, and this device is used to execute the above method.

[0015] To solve the above technical problems, the present application also provides a sludge return control system based on AI decision control. The system includes the above-mentioned sludge return control device based on AI decision control; the system also includes several sensors for detecting flow rates installed on the influent pipe and the sludge discharge pipe; among them, the sludge return control device based on AI decision control is signal-connected to the sensors.

[0016] The sludge return control method based on AI decision control provided by the present application, as well as the corresponding device and system. In the method provided by the present application, by obtaining the execution mode command input by the user and judging the corresponding execution mode according to the execution mode command, starting the corresponding program according to the corresponding execution mode, and based on the AI decision according to the sludge discharge / water discharge data obtained in real time, controlling the opening and closing of the sludge discharge pump and the pump frequency adjustment of the water discharge flow pump; the sludge return control method based on AI decision control provided by the present application can accurately control the sludge discharge / water discharge amount based on AI decision, and realize the real-time and efficient processing and accurate control of the sludge discharge / water discharge data.

[0017] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specific preferred embodiments are given and described in detail in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic data flow diagram of the sludge return control method based on AI decision control in an embodiment of the present application.

[0019] Figure 2 It is a schematic data flow diagram of the sludge return control method based on AI decision control in another embodiment of the present application.

[0020] Figure 3 It is a schematic framework diagram of the sludge return control device based on AI decision control in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To further elaborate on the technical means and effects adopted by the present application to achieve the predetermined application purpose, the following is a detailed description of the present application in conjunction with the accompanying drawings and preferred embodiments.

[0022] Through the description of the specific embodiments, a more in-depth and specific understanding of the technical means and effects adopted by the present application to achieve the predetermined purpose can be obtained. However, the accompanying drawings are only for reference and illustration, and are not used to limit the present application.

[0023] Embodiment 1

[0024] Please refer to Figure 1, the sludge return control method based on AI decision control in this embodiment includes: 101. Obtain the execution mode command input by the user, and judge the corresponding execution mode according to the execution mode command; in the sludge return control method based on AI decision control provided in the embodiment of the present invention, the user can conveniently and independently set corresponding parameters through the front-end interaction interface of the sludge return control device based on AI decision control. The user selects the execution mode to be started. After the sludge return control device based on AI decision control obtains it, it judges the specific start mode according to the execution mode command; 102. Obtain the preset expected sludge discharge amount data and pump frequency data; if the judgment result is to start the sludge discharge mode, the user sets the expected sludge discharge amount data and the pump frequency data of the sludge discharge pump according to actual needs, and the sludge return control device based on AI decision control obtains this data and the pump frequency data; 103. Turn on the sludge discharge pump and set the pump frequency of the sludge discharge pump according to the pump frequency data; the sludge return control device based on AI decision control turns on the sludge discharge pump and sets the pump frequency of the sludge discharge pump according to the obtained pump frequency data; 104. Real-time obtain the current sludge discharge amount data; the sludge return control device based on AI decision control turns on real-time monitoring of the cumulative sludge discharge amount, and realizes real-time obtaining of the current sludge discharge amount data through data interaction with the sensor for monitoring the cumulative sludge discharge flow rate on the sludge discharge pipeline in the sludge return control system based on AI decision control. This data includes: cumulative sludge discharge amount data and real-time sludge discharge amount data; 105. When the current sludge discharge amount data is not less than the expected sludge discharge amount data, turn off the sludge discharge pump; after the sludge return control device based on AI decision control obtains the cumulative sludge discharge amount data and the real-time sludge discharge amount data in real time, it calculates in real time whether the cumulative sludge discharge amount data is not less than the expected sludge discharge amount data set by the user according to actual needs. If so, it automatically turns off the sludge discharge pump to ensure accurate quantitative control of the sludge discharge operation and avoid resource waste and operation errors.

[0025] In this embodiment, this method obtains the execution mode command input by the user and judges the corresponding execution mode according to this execution mode command. If it is judged to be the sludge discharge mode, it obtains the preset expected sludge discharge amount data, turns on the sludge discharge pump, and real-time obtains the current sludge discharge amount data until the current sludge discharge amount data is greater than the expected sludge discharge amount data, then turns off the sludge discharge pump; the sludge return control method based on AI decision control provided in this application can intelligently obtain real-time sewage discharge data according to the sewage discharge execution mode currently selected by the user, and track and judge the real-time sewage discharge data, and turn off the sludge discharge pump according to the judgment result; realizing real-time monitoring of sewage discharge data, efficient processing of real-time data, and accurate control of the sludge discharge amount.

[0026] Embodiment 2

[0027] Please refer to Figure 2The sludge return control method based on AI decision control in this embodiment includes: 201. Receive time series data input by a sensor; The sludge return control device based on AI decision control exchanges data by connecting with the flow sensor signal that monitors the cumulative water inflow on the water inlet pipe in the sludge return control system based on AI decision control; and by connecting with the sensor signal that monitors the cumulative sludge discharge on the sludge discharge pipe; The sludge return control device based on AI decision control receives the time series data input by the sensor, which mainly includes the water inlet time and the corresponding water inlet volume, the sludge / drainage time and the corresponding sludge / drainage volume; 202. Clean, fill, and sort the time series data to form new time series data; Clean, fill and sort the time series data. Specifically: Identify invalid input values ​​in time series data, including negative numbers, None values, abnormally large values ​​far beyond the reasonable range, null, non-numeric data, etc.; then remove invalid input values; and then fill the removed vacant positions with numbers. Specifically, fill the vacant positions in the cleaned time series data with numbers according to the mean filling method, or fill the vacant positions in the cleaned time series data with numbers according to the median filling method; Then sort the filled time series data by time to form new time series data; After the sludge return control device based on AI decision control is started, steps 201 and 202 are executed to obtain time series data and then process the time series data to form new time series data; 203. Obtain the execution mode command input by the user; the user conveniently and autonomously sets the corresponding parameters through the interactive interface of the sludge return control device based on AI decision-making control at the front end, and the user selects the execution mode to be started; 204. Determine the corresponding execution mode according to the execution mode command; after the sludge return flow control device based on AI decision control obtains the execution mode selected by the user to be started, determine the specific start mode according to the execution mode command; 205. Obtaining preset expected sludge discharge volume data and pump frequency data; if the judgment result is to start the sludge discharge mode, the user sets the expected sludge discharge volume data and the pump frequency data of the sludge discharge pump according to actual needs, and the sludge return control device based on AI decision control obtains the data and pump frequency data; 206. Start the sludge pump and set the pump frequency of the sludge pump according to the pump frequency data; the sludge return control device based on AI decision control starts the sludge pump and sets the pump frequency of the sludge pump according to the acquired pump frequency data; 207. Obtain the current sludge discharge volume data in real time; the sludge return control device based on AI decision control starts real-time monitoring of the cumulative sludge discharge volume, and realizes real-time acquisition of the current sludge discharge volume data through data interaction with the sensor for monitoring the cumulative sludge discharge volume on the sludge discharge pipeline in the sludge return control system based on AI decision control. This data includes: cumulative sludge discharge volume data and real-time sludge discharge volume data; 208. Judge whether the current sludge discharge volume data is not less than the expected sludge discharge volume data; after the sludge return control device based on AI decision control obtains the cumulative sludge discharge volume data and the real-time sludge discharge volume data in real time, it calculates in real time whether the cumulative sludge discharge volume data is not less than the expected sludge discharge volume data set by the user according to actual needs, that is, judges whether the current sludge discharge volume data is not less than the expected sludge discharge volume data. If so, execute step 217 to automatically turn off the sludge discharge pump to ensure the precise quantitative control of the sludge discharge operation and avoid resource waste and operation errors; 209. Obtain the manually set target drainage flow rate target value; if the judgment result is the manual setting flow rate target mode, the user sets the manually set target drainage flow rate target value according to actual needs, and the sludge return control device based on AI decision control obtains the manually set target drainage flow rate target value set by the user; 210. Start the drainage flow pump and obtain the real-time drainage volume data at a preset frequency; the sludge return control device based on AI decision control starts the drainage flow pump and obtains the drainage volume data obtained by the sensor on the drainage pipeline at a preset frequency; 211. Judge whether the real-time drainage volume data is within the range of the manually set target drainage flow rate target value ±X; after obtaining the drainage volume data obtained by the sensor on the drainage pipeline, judge whether the real-time drainage volume data is within the range of the manually set target drainage flow rate target value ±X according to the manually set target drainage flow rate target value. If not, execute step 212; if so, execute step 217 to maintain the pump frequency of the drainage flow pump, so that the drainage volume can be stably and precisely maintained within a small fluctuation range near the manually set target drainage flow rate target value, so as to ensure the precise quantitative control of the drainage operation and avoid resource waste and operation errors. Among them, the value of X is set according to the on-site error tolerance range. Specifically, the value of X can be determined within the range of ±5% of the manually set target drainage flow rate target value according to the on-site situation; 212. Use the PID control algorithm to calculate the adjustment amount of the pump frequency and adjust the pump frequency; if the difference between the manually set target drainage flow rate target value and the real-time drainage volume data is greater than the preset difference, it is judged that the real-time drainage volume data is not within the range of the manually set target drainage flow rate target value ±X, and the drainage work needs to continue; then use the PID control algorithm to calculate the adjustment amount of the pump frequency and adjust the pump frequency. Specifically: Calculate the adjustment amount of the pump frequency in real time: ; Among them, is the last value of the flow gap time series , is the second last value of the flow gap time series , is the change trend of the flow gap time series, is the shortest adjustment time interval of the valve, K represents the adjustment strength, and is set through experimental results in actual deployment.

[0028] Dynamically adjust the pump frequency in real time according to the calculated adjustment amount of the pump frequency, and then return to step 211 to continue the step of judging whether the real-time drainage volume data is within the range of the manually set target drainage flow target value ±X. Repeat this cycle until the real-time drainage volume data is within the range of the manually set target drainage flow target value ±X, then execute step 217 to turn off the drainage flow pump; by implementing dynamic and intelligent control of the pump frequency of the drainage flow pump, the drainage flow can be stably and accurately maintained within a small fluctuation range near the target value, so as to meet diverse drainage flow demand scenarios and ensure the stability and accuracy of drainage; 213. Obtain the flow data of the water inlet at a preset frequency; if the judgment result is the automatic setting of the flow target mode, the sludge return control device based on AI decision control obtains the flow data of the water inlet at a preset frequency; 214. Turn on the drainage flow pump and obtain the real-time drainage volume data at a preset frequency; the sludge return control device based on AI decision control turns on the drainage flow pump and obtains the drainage volume data obtained by the sensor on the drainage pipeline at a preset frequency; 215. Obtain the automatic target drainage flow target value; obtain the automatic target drainage flow target value, which is determined according to on-site data such as the flow data of the water inlet and the real-time drainage volume data; 216. Turn on or off the drainage flow pump according to the automatic target drainage flow target value; the sludge return control device based on AI decision control judges whether it is necessary to turn on the drainage flow pump for drainage work or turn off the drainage flow pump to end the drainage work according to the automatic target drainage flow target value. Specifically: After obtaining the drainage volume data obtained by the sensor on the drainage pipeline, judge whether the real-time drainage volume data is within the range of the automatic target drainage flow target value ±X according to the automatic target drainage flow target value. If so, execute step 217 to automatically turn off the drainage flow pump, so that the drainage volume can be stably and accurately maintained within a small fluctuation range near the automatic target drainage flow target value, realizing automated and efficient fluid processing without human intervention, greatly improving the system operation efficiency and accuracy, and reducing the human cost and the risk of operation errors; among them, the value of X is set according to the on-site error tolerance range. Specifically, the value of X can be determined within the range of ±5% of the automatic target drainage flow target value according to the on-site situation; If the answer is no, use the PID control algorithm to calculate the adjustment amount of the pump frequency and adjust the pump frequency. Specifically: Calculate the adjustment amount of the pump frequency in real time: ; where is the last value of the flow gap time series of is the second last value of the flow gap time series of is the change trend of the flow gap time series, is the shortest adjustment time interval of the valve, K represents the adjustment strength, and is set through experimental results in actual deployment.

[0029] Dynamically adjust the pump frequency in real time according to the calculated adjustment amount of the pump frequency, and then return to the step of judging whether the real-time drainage volume data is within the range of the automatic target drainage flow target value ±X, and loop in this way until the real-time drainage volume data is within the range of the automatic target drainage flow target value ±X, then execute step 217 to maintain the pump frequency of the drainage flow pump; by dynamically and intelligently controlling the pump frequency of the drainage flow pump, the drainage flow can be stably and accurately maintained within a small fluctuation range near the target value, so as to meet diverse drainage flow demand scenarios, ensure the stability and accuracy of drainage, realize automated and efficient fluid processing without human intervention, greatly improve the system operation efficiency and accuracy, and reduce the human cost and operation error risk; 217. Close the sludge discharge pump / adjust the pump frequency of the drainage flow pump.

[0030] In this embodiment, the method realizes real-time monitoring of drainage / sludge discharge data, efficient processing of real-time data, and accurate control of drainage / sludge discharge volume in multiple modes by obtaining the execution mode command input by the user and judging the corresponding execution mode according to the execution mode command, and opening the corresponding drainage / sludge discharge process, so as to meet diverse drainage / sludge discharge flow demand scenarios.

[0031] Embodiment 3

[0032] Please refer to Figure 3 , the sludge return control device based on AI decision control in this embodiment includes: An interaction module 301 for realizing human-computer interaction; An algorithm control module 302 for executing the data processing flow in Embodiment 1 or Embodiment 2. For the specific process, please refer to Embodiment 1 and Embodiment 2, which will not be elaborated here.

[0033] In this embodiment, in the sludge return control device based on AI decision control, the algorithm control module determines the corresponding execution mode according to the execution mode command input by the user, and starts the corresponding drainage / sludge discharge process according to the execution mode, realizing real-time monitoring of drainage / sludge discharge data, efficient processing of real-time data, and precise control of drainage / sludge discharge volume under multiple modes, meeting diverse drainage / sludge discharge flow demand scenarios.

[0034] Embodiment 4

[0035] Please refer to Figure 3 , the sludge return control system based on AI decision control in this embodiment includes the sludge return control device based on AI decision control in Embodiment 3; the sludge return control system based on AI decision control in this embodiment further includes several sensors for detecting flow rates installed on the inlet pipe and the sludge discharge / drainage pipe, wherein the sludge return control device based on AI decision control is signal-connected to the aforementioned sensors.

[0036] In this embodiment, in the sludge return control system based on AI decision control, the sludge return control device based on AI decision control determines the corresponding execution mode according to the execution mode command input by the user, starts the corresponding drainage / sludge discharge process according to the execution mode, realizes signal interaction according to the signals connected to several sensors for detecting flow rates installed on the inlet pipe and the drainage / sludge discharge pipe, and monitors the data of the inlet pipe and / or the drainage / sludge discharge pipe in real time, realizing real-time monitoring of drainage / sludge discharge data, efficient processing of real-time data, and precise control of drainage / sludge discharge volume under multiple modes, meeting diverse drainage / sludge discharge flow demand scenarios.

Claims

1. A sludge return control method based on AI decision-making control, characterized in that, The method includes: Obtain an execution mode command input by a user, and determine the corresponding execution mode according to the execution mode command; If it is determined to be the sludge discharge mode, obtain preset expected sludge discharge amount data and pump frequency data; Turn on the sludge discharge pump and set the pump frequency of the sludge discharge pump according to the pump frequency data; Obtain the current sludge discharge amount data in real time; When the current sludge discharge amount data is not less than the expected sludge discharge amount data, turn off the sludge discharge pump.

2. The method according to claim 1, characterized in that, The method further includes: If it is determined to be the manual setting of flow target mode, obtain the manually set target drainage flow target value; turn on the drainage flow pump, and obtain the real-time drainage amount data at a preset frequency; Judge whether the real-time drainage amount data is within the range of the manually set target drainage flow target value ±X; If the real-time drainage amount data is not within the range of the manually set target drainage flow target value ±X, use the PID (Proportional-Integral-Derivative) control algorithm to calculate the adjustment amount of the pump frequency, and then adjust the pump frequency according to the adjustment amount of the pump frequency; Return to the step of judging whether the real-time drainage amount data is within the range of the manually set target drainage flow target value ±X, until the real-time drainage amount data is within the range of the manually set target drainage flow target value ±X, then keep the drainage flow pump frequency unchanged.

3. The method according to claim 1, wherein The method further includes: If it is determined to be the automatic setting of flow target mode, obtain the flow data of the water inlet in real time at a preset frequency; Calculate the automatic drainage flow target value according to the flow data of the water inlet and the real-time drainage amount data; Adjust the pump frequency of the drainage flow pump according to the automatic drainage flow target value.

4. The method according to claim 3, wherein The step of adjusting the pump frequency of the drainage flow pump according to the automatic drainage flow target value includes: Judge whether the real-time drainage amount data is within the range of the automatic target drainage flow target value ±X; If the real-time drainage amount data is not within the range of the automatic target drainage flow target value ±X, use the PID control algorithm to calculate the adjustment amount of the pump frequency, and adjust the pump frequency according to the adjustment amount of the pump frequency.

5. The method according to claim 2 or 4, characterized in that, The step of using the PID control algorithm to calculate the adjustment amount of the pump frequency specifically includes: Use the following formula to calculate the adjustment amount of the pump frequency in real time: ； Among them, is the last value of the flow gap time series , is the second last value of the flow gap time series , is the change trend of the flow gap time series, is the shortest adjustment time interval of the valve, and K represents the adjustment strength.

6. The method according to claim 1, characterized in that, Before the step of obtaining the execution mode command input by the user, it further includes: Receive the time series data input by the sensor; Clean the time series data; Fill in the missing positions in the cleaned time series data with numbers; Sort the filled time series data according to time to form a new time series data.

7. The method according to claim 6, characterized in that The step of cleaning the time series data includes: Identify the invalid input values in the time series data; Eliminate the invalid input values.

8. The method according to claim 7, wherein The step of filling in the missing positions in the cleaned time series data with numbers includes: Fill in the missing positions in the cleaned time series data with numbers according to the mean filling method; or Fill in the missing positions in the cleaned time series data with numbers according to the median filling method.

9. A sludge return control device based on AI decision-making control, characterized in that, The device is used to execute the method described in any one of claims 1 to 8.

10. A sludge return control system based on AI decision-making control, characterized in that, The system includes the sludge return control device based on AI decision-making control described in claim 9; the system further includes a number of sensors for detecting flow rates installed on the influent pipeline and the sludge discharge pipeline; the sludge return control device based on AI decision-making control is signal-connected to the sensors.

Images